Abstract. Automated annotation of web documents is a key challenge of the Semantic Web effort. Semantic metadata can be created manually or using automated annotation or tagging tools. Automated semantic annotation tools with best results are built on various machine learning algorithms which require training sets. Other approach is to use pattern based semantic annotation solutions built on natural language processing, information retrieval or information extraction methods. The paper presents Ontea platform for automated semantic annotation or semantic tagging. Implementation based on regular expression patterns is presented with evaluation of results. Extensible architecture for integrating pattern based approaches is presented. Most of existing semi-automatic annotation solutions can not prove it real usage on large scale data such as web or email communication, but semantic web can be exploited only when computer understandable metadata will reach critical mass. Thus we also present approach to large scale pattern based annotation.

Abstract. Many keyword-based approaches to text classification, information retrieval or even user modeling for adaptive web-based system could benefit from knowledge on relations between various keywords, which gives further possibilities to compare them, evaluate their distance etc. This paper proposes an approach how to determine keyword relations (mainly a parent-child relationship) by leveraging collective wisdom of the masses, present in data of collaborative (social) tagging systems on the Web. The feasibility of our approach is demonstrated on the data coming from the social bookmarking systems delicious and CiteULike. 1

Abstract. Growing need for information retrieval, information processing, and the associated need for navigation in existing information spaces resulted in several approaches that aim to improve efficiency of the respective user tasks. However, problems related to user navigation and orientation in large open information spaces still persist possibly due to increasing demands and the imperfections of individual approaches. We propose an integrated search and navigation solution that takes advantage of the faceted browsing paradigm and visual navigation in graphs both extended with support for automatic personalization based on user context also taking advantage of a user’s social network. The proposed solution is primarily evaluated in the domain of scientific publications, i.e. digital libraries, with possible extensions to other application domains. 1

Abstract—Many approaches have been developed to simplify user navigation and information search in large information spaces. Annotations, i.e. notes, comments, explanations or other types of remarks bring to these activities new dimension. Annotations enrich the content and also support collaboration. This paper presents a method for annotation learning materials on programming. Learning materials in domain of programming consist of text mixed with programming exercises and code samples. The main idea of the annotation is an extension of learning materials by additional information helping students to understand learning subject easier and faster together with minimizing a need of finding supplemental information in external sources such as reference guides. Additionally, user annotations provide a context based communication space for students and their teacher: students add annotations into the learning text to ask, suggest or comment and the teacher evaluates the annotations and responds. To verify value of this approach we tested proposed method for annotation learning texts within an existing learning system in domain of functional and logic programming. Keywords-learning text annotation; automatic annotation; generic annotation; context annotation; learning programming; I.

Abstract. Motivation as key factor for maintaining effective learning must be maintained during computer-supported learning. For this, we attempt to investigate the benefits of a socially intelligent tutoring agent that goes beyond attending to aspects of an individual student, the tutoring friend. In a computer-supported learning system, a tutoring friend is an artificial agent that manages relationships with learners, monitors their social behavior, and is able to assemble socially-aware groups for peer collaboration. We hypothesize that intelligent tutoring friends can motivate students to long-term participation by the virtue of social affordances they provide.

Abstract. Acquiring information from the Web is a demanding task and currently subject of a world-wide research. In this paper we focus on research of methods, and experience with development of software tools designed for retrieval, organization, presentation of information in heterogeneous data source spaces such as the Web. We see the Web as a unique evolving and unbounded information system. The presented concepts can be used also in other specific contexts of information systems in organizations that increasingly become worldwide and weaved together considering information processing. 1

Web portals contain large amount of information. Users could really benefit from it if personalized presentation is used. For this to be accomplished the website needs to “know ” its users. When surfing the Web users leave digital footprints in the form of navigational paths and actions taken. We present a method for adaptive navigation support and link recommendation. The method is based on an analysis of the user’s navigational patterns and behavior on the web pages while browsing through a web portal. We extract interesting information from a web portal and then recommend it. Finally, we provide our experience with a recommender system deployed on our faculty’s website, which recommends events by means of personalized calendar.